
import pandas as pd
import plotly as plt
import numpy as np

pd.options.display.max_rows = 4000

import matplotlib.pyplot as plt
import seaborn as sns
plt.style.use('ggplot')

import plotly.express as px 
import plotly.subplots as tls
import plotly
import plotly.offline as py
from plotly.offline import init_notebook_mode, iplot, plot
import plotly.graph_objs as go
init_notebook_mode(connected=True)

from pandas_profiling import ProfileReport

from sklearn.preprocessing import LabelEncoder, OneHotEncoder
from sklearn.model_selection import train_test_split, KFold, RandomizedSearchCV, GridSearchCV, StratifiedShuffleSplit
from sklearn.decomposition import PCA
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import StandardScaler
from sklearn.ensemble import RandomForestClassifier
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import roc_auc_score
from sklearn.metrics import confusion_matrix
from sklearn.metrics import classification_report

SEED = 42


from io import StringIO
import re

for_pd = StringIO()
with open("data/kickstarter/ks-projects-201612.csv") as data_file:
    for line in data_file:
        new_line = re.sub(r', ', ';', line.rstrip(), count=17)
        print (new_line, file=for_pd)

for_pd.seek(0)

df = pd.read_csv(for_pd, sep=',',low_memory=False)
df = df.rename(columns=lambda x: x.strip())


df=df.dropna(axis=1,how='all')
df2 = df[df["Unnamed: 13"].notnull()].copy(deep=True)
df = df[df["Unnamed: 13"].isnull()]
df=df.dropna(axis=1,how='all')


df.head()


df2.count()

ID               34
name             34
category         29
main_category    34
currency         34
deadline         34
goal             34
launched         34
pledged          34
state            34
backers          34
country          34
usd pledged      34
Unnamed: 13      34
dtype: int64


df.describe()


df[df['name'].isnull()]


df.dropna(subset = ["name"], inplace=True)


df.isnull().any()

ID               False
name             False
category         False
main_category    False
currency         False
deadline         False
goal             False
launched         False
pledged          False
state            False
backers          False
country          False
usd pledged       True
dtype: bool


df['usd pledged'] = np.where(df['main_category'] == 'USD', df['country'], df['usd pledged'])
df['country'] = np.where(df['main_category'] == 'USD', df['backers'], df['country'])
df['backers'] = np.where(df['main_category'] == 'USD', df['state'], df['backers'])
df['state'] = np.where(df['main_category'] == 'USD', df['pledged'], df['state'])
df['pledged'] = np.where(df['main_category'] == 'USD', df['launched'], df['pledged'])
df['launched'] = np.where(df['main_category'] == 'USD', df['goal'], df['launched'])
df['goal'] = np.where(df['main_category'] == 'USD', df['deadline'], df['goal'])
df['deadline'] = np.where(df['main_category'] == 'USD', df['currency'], df['deadline'])
df['currency'] = np.where(df['main_category'] == 'USD', df['main_category'], df['currency'])


df['tmp'] = df['category']
df['category'] = np.where(df['main_category'] == 'USD', df['name'], df['category'])


df['name'] = np.where(df['main_category'] == 'USD', df['ID'].str.split(';').str[-1], df['name'])


df['ID'] = np.where(df['main_category'] == 'USD', df['ID'].str.split(';').str[0], df['ID'])


df[df['main_category']=='USD']


df['main_category'] = np.where(df['main_category'] == 'USD', df['tmp'], df['main_category'])
df = df.drop(columns=['tmp'])


df.describe()


df['country'] = df['country'].replace(['N,"0'],[None])


df['country'].value_counts(dropna=False)

US     258051
GB      27568
CA      12007
AU       6251
NaN      3797
DE       2684
NL       2265
FR       1911
IT       1750
ES       1373
SE       1271
NZ       1137
DK        825
IE        576
NO        526
CH        471
BE        402
AT        377
MX        214
SG        119
HK         97
LU         40
Name: country, dtype: int64


df.dtypes

ID               object
name             object
category         object
main_category    object
currency         object
deadline         object
goal             object
launched         object
pledged          object
state            object
backers          object
country          object
usd pledged      object
dtype: object


df.isnull().any()

ID               False
name             False
category         False
main_category    False
currency         False
deadline         False
goal             False
launched         False
pledged          False
state            False
backers          False
country           True
usd pledged       True
dtype: bool


df2.isnull().any()

ID               False
name             False
category          True
main_category    False
currency         False
deadline         False
goal             False
launched         False
pledged          False
state            False
backers          False
country          False
usd pledged      False
Unnamed: 13      False
dtype: bool


df2.head()


df2['tmp'] = df2['category']

df2['category'] = df2['main_category']
df2['main_category'] = df2['currency']
df2['currency'] = df2["deadline"]
df2["deadline"] = df2["goal"]
df2["goal"] = df2["launched"]
df2["launched"] = df2["pledged"]
df2['pledged'] = df2['state']
df2["state"] = df2["backers"]
df2["backers"] = df2["country"]
df2["country"] = df2["usd pledged"]
df2["usd pledged"] = df2["Unnamed: 13"]


df2['name'] = np.where(~df2['tmp'].isnull(), df2['name']+df2['tmp'], df2['name'])


df2 = df2.drop(columns=['tmp', 'Unnamed: 13'])


df2.isnull().any()

ID               False
name             False
category         False
main_category    False
currency         False
deadline         False
goal             False
launched         False
pledged          False
state            False
backers          False
country          False
usd pledged      False
dtype: bool


df2.state.value_counts(dropna=False)

failed        22
canceled       6
successful     6
Name: state, dtype: int64


df = df.append(df2, ignore_index=True)


df.describe()


df[df["country"].isnull()].shape

(3797, 13)


df[df["usd pledged"].isnull()].shape

(3797, 13)


df[df['usd pledged'].isnull()].all() == df[df['country'].isnull()].all()

ID               True
name             True
category         True
main_category    True
currency         True
deadline         True
goal             True
launched         True
pledged          True
state            True
backers          True
country          True
usd pledged      True
dtype: bool


# Converting the columns into the right dtypes as for dates and numbers.

df["deadline"] = pd.to_datetime(df['deadline'])
df["launched"] = pd.to_datetime(df['launched'])
df["ID"] = pd.to_numeric(df["ID"])
df["goal"] = pd.to_numeric(df["goal"])
df["pledged"] = pd.to_numeric(df["pledged"])
df["backers"] = pd.to_numeric(df["backers"])
df["usd pledged"] = pd.to_numeric(df["usd pledged"])


df.dtypes

ID                        int64
name                     object
category                 object
main_category            object
currency                 object
deadline         datetime64[ns]
goal                    float64
launched         datetime64[ns]
pledged                 float64
state                    object
backers                   int64
country                  object
usd pledged             float64
dtype: object


import matplotlib.pyplot as plt
import seaborn as sns
plt.style.use('ggplot')
import plotly
import  plotly.offline as py
py.init_notebook_mode(connected=True)
#import plotly.plotly as py
import plotly.graph_objs as go


import plotly.express as px
fig = px.bar(df["state"].value_counts().rename_axis('state').reset_index(name='counts'), y="state", x="counts", color="state", orientation="h", hover_name="counts",
             color_discrete_sequence= px.colors.qualitative.Plotly,
             title="State-counts plot"
            )

fig.show()


import plotly.express as px
fig = px.pie(df["state"].value_counts(dropna=False).rename_axis('state').reset_index(name='counts'), values='counts', names='state', title='Repartition of states amongst Kickstarters projects')
fig.show()


df_final = df[(df["state"] == "failed") | (df["state"] == "successful")].copy()


import plotly.express as px
fig = px.pie(df_final["state"].value_counts(dropna=False).rename_axis('state').reset_index(name='counts'), values='counts', names='state', title='Repartition of states amongst Kickstarters projects')
fig.show()


df_final.isnull().any()

ID               False
name             False
category         False
main_category    False
currency         False
deadline         False
goal             False
launched         False
pledged          False
state            False
backers          False
country           True
usd pledged       True
dtype: bool


df_final[["currency",'usd pledged', 'pledged']]


(df_final[df_final["currency"]=='USD'][df_final["pledged"]==df_final["usd pledged"]].shape[0]*100)/(df_final[df_final["currency"]=='USD'].shape[0])

<ipython-input-42-e7548e3a79ea>:1: UserWarning:

Boolean Series key will be reindexed to match DataFrame index.

94.85552777475813


import plotly.express as px
fig = px.pie(df_final["currency"].value_counts(dropna=False).rename_axis('currency').reset_index(name='counts'), values='counts', names='currency', title='Repartition of currencies amongst projects')
fig.show()


df_final[df_final["pledged"]==df_final["usd pledged"]][df_final["pledged"]!=0].currency.value_counts()

<ipython-input-44-bf9449f4f9b2>:1: UserWarning:

Boolean Series key will be reindexed to match DataFrame index.

USD    192617
GBP         1
Name: currency, dtype: int64


#df_final[df_final["pledged"]==df_final["real_usd_pledged"]][df_final["pledged"]!=0].currency.value_counts()


df_final[df_final["pledged"]==df_final["usd pledged"]][df_final["pledged"]!=0][df_final["currency"]=="GBP"]

<ipython-input-46-3a8822307e07>:1: UserWarning:

Boolean Series key will be reindexed to match DataFrame index.


df_final = pd.read_csv('out2.zip')


df_final = df_final.drop(['goal', 'pledged', 'usd pledged'], axis = 1)


df_final.describe(include='all')


# Converting the columns into the right dtypes as for dates and numbers.
df_final["deadline"] = pd.to_datetime(df_final['deadline'])
df_final["launched"] = pd.to_datetime(df_final['launched'])
df_final["ID"] = pd.to_numeric(df_final["ID"])
# df_final["goal"] = pd.to_numeric(df_final["goal"])
# df_final["pledged"] = pd.to_numeric(df_final["pledged"])
df_final["backers"] = pd.to_numeric(df_final["backers"])
# df_final["usd pledged"] = pd.to_numeric(df_final["usd pledged"])
df_final["real_usd_pledged"] = pd.to_numeric(df_final["real_usd_pledged"])
df_final["usd_goal"] = pd.to_numeric(df_final["usd_goal"])


df_final.dtypes

ID                           int64
name                        object
category                    object
main_category               object
currency                    object
deadline            datetime64[ns]
launched            datetime64[ns]
state                       object
backers                      int64
country                     object
real_usd_pledged           float64
usd_goal                   float64
dtype: object


df_final.isnull().any()

ID                  False
name                False
category            False
main_category       False
currency            False
deadline            False
launched            False
state               False
backers             False
country              True
real_usd_pledged    False
usd_goal            False
dtype: bool


df_final[df_final['country'].isnull()].head()


df_final[df_final['country'].isnull()].shape

(210, 12)


df_final = df_final[~df_final['country'].isnull()]


df_final = df_final.loc[~((df_final['real_usd_pledged']>=df_final['usd_goal']) & (df_final['state']=='failed'))]


df_final = df_final.reset_index(drop=True)


df_final.isnull().any()

ID                  False
name                False
category            False
main_category       False
currency            False
deadline            False
launched            False
state               False
backers             False
country             False
real_usd_pledged    False
usd_goal            False
dtype: bool


df_final.shape

(281637, 12)


df_final.duplicated().sum()

0


counts = df_final['name'].value_counts().rename_axis('name').reset_index(name='counts')


duplicate_names = df_final[df_final['name'].isin(counts[counts['counts']>1].name.tolist())]


duplicate_names.shape

(3022, 12)


duplicate_names.sort_values(by=['name']).head()


def plot_cat_value_counts(df: pd.DataFrame, column: str, legend_name: str, state: str="state", num:int=-1, normalize:bool=True):
    main_cats = df[column].value_counts().head(num)
    main_cats_failed = df[df[state] == "failed"][column].value_counts(normalize=normalize).head(num)
    main_cats_sucess = df[df[state] == "successful"][column].value_counts(normalize=normalize).head(num)

    #First plot
    trace0 = go.Bar(
        x=main_cats_failed.index,
        y=main_cats_failed.values,
        name="Failed "+ legend_name
    )
    #Second plot
    trace1 = go.Bar(
        x=main_cats_sucess.index,
        y=main_cats_sucess.values,
        name="Successful "+ legend_name
    )
    #Third plot
    trace2 = go.Bar(
        x=main_cats.index,
        y=main_cats.values,
        name= legend_name +" Distribution"
    )

    #Creating the grid
    fig = tls.make_subplots(rows=2, cols=2, specs=[[{}, {}], [{'colspan': 2}, None]],
                            subplot_titles=('Failed','Sucessful', "General "+ legend_name), vertical_spacing = 0.4)

    #setting the figs
    fig.append_trace(trace0, 1, 1)
    fig.append_trace(trace1, 1, 2)
    fig.append_trace(trace2, 2, 1)
    
    fig['layout'].update(showlegend=True,
                         title=column.upper().replace("_"," ")+" Distribution",
                         title_x=0.43,
                         bargap=0.1)
    iplot(fig)


plot_cat_value_counts(df_final, "main_category", "Categories")


plot_cat_value_counts(df_final, "category", "Sub_categories", num = 15, normalize=False)


df_final['cat_full'] = df_final[["main_category","category"]].agg('-'.join, axis=1)


df_final[['cat_full', 'category']].describe()


main_cats_failed = df_final[df_final["state"] == "failed"]["main_category"].value_counts()
main_cats_success = df_final[df_final["state"] == "successful"]["main_category"].value_counts()

#First plot
trace1 = go.Bar(
    x=main_cats_success.index,
    y=main_cats_success.values,
    opacity=0.60,
    name="Successful Categories"
)

#Second plot
trace2 = go.Bar(
    x=main_cats_failed.index,
    y=main_cats_failed.values,
    opacity=0.60,
    name="Failed Categories"
)


data = [trace1, trace2]
layout = go.Layout(barmode='overlay', title=go.layout.Title(text="Failed and Success over Main categories"))

fig = go.Figure(
    data=data,
    layout=layout
)

iplot(fig)


main_cats_failed = df_final[df_final["state"] == "failed"]["cat_full"].value_counts()
main_cats_success = df_final[df_final["state"] == "successful"]["cat_full"].value_counts()


dico = main_cats_failed.to_dict()
for k in dico.keys():
    dico[k] = (dico[k],main_cats_success[k])

more_success_than_failed = {k:v for k,v in dico.items() if v[0]<v[1]}
more_failed_than_success = {k:v for k,v in dico.items() if v[0]>=v[1]}

#First plot
trace1 = go.Bar(
    x=main_cats_success[main_cats_success.index.isin(list(more_success_than_failed.keys()))].index,
    y=main_cats_success[main_cats_success.index.isin(list(more_success_than_failed.keys()))].values,
    opacity=0.60,
    name="Successful Categories"
)

#Second plot
trace2 = go.Bar(
    x=main_cats_failed[main_cats_failed.index.isin(list(more_success_than_failed.keys()))].index,
    y=main_cats_failed[main_cats_failed.index.isin(list(more_success_than_failed.keys()))].values,
    opacity=0.60,
    name="Failed Categories"
)

data = [trace1, trace2]
layout = go.Layout(barmode='overlay', title=go.layout.Title(text="Most success in categories"))

fig = go.Figure(
    data=data,
    layout=layout
)

iplot(fig)


#First plot
trace1 = go.Bar(
    x=main_cats_success[main_cats_success.index.isin(list(more_failed_than_success.keys()))].index,
    y=main_cats_success[main_cats_success.index.isin(list(more_failed_than_success.keys()))].values,
    opacity=0.60,
    name="Successful Categories"
)

#Second plot
trace2 = go.Bar(
    x=main_cats_failed[main_cats_failed.index.isin(list(more_failed_than_success.keys()))].index,
    y=main_cats_failed[main_cats_failed.index.isin(list(more_failed_than_success.keys()))].values,
    opacity=0.60,
    name="Failed Categories"
)

data = [trace1, trace2]
layout = go.Layout(barmode='overlay', title=go.layout.Title(text="Most failed in categories"))

fig = go.Figure(
    data=data,
    layout=layout
)

iplot(fig)


print("The most promising categories to start a kickstarter in are:",", ".join(list(more_success_than_failed.keys())))

The most promising categories to start a kickstarter in are: Music-Music, Film & Video-Shorts, Games-Tabletop Games, Music-Rock, Theater-Theater, Comics-Comics, Music-Indie Rock, Music-Pop, Music-Country & Folk, Art-Public Art, Art-Illustration, Publishing-Art Books, Music-Classical Music, Comics-Comic Books, Dance-Dance, Music-Jazz, Comics-Graphic Novels, Theater-Plays, Theater-Musical, Technology-DIY Electronics, Dance-Performances, Comics-Webcomics, Art-Installations, Theater-Festivals, Technology-Camera Equipment, Theater-Experimental, Music-Punk, Theater-Immersive, Film & Video-Festivals, Publishing-Literary Journals, Publishing-Anthologies, Theater-Spaces, Crafts-Knitting, Comics-Anthologies, Crafts-Pottery, Design-Typography, Dance-Residencies, Crafts-Letterpress, Music-Chiptune


print("The less promising categories to start a kickstarter in are:",", ".join(list(more_failed_than_success.keys())))

The less promising categories to start a kickstarter in are: Design-Product Design, Film & Video-Documentary, Food-Food, Games-Video Games, Publishing-Fiction, Film & Video-Film & Video, Fashion-Fashion, Publishing-Nonfiction, Technology-Apps, Technology-Technology, Fashion-Apparel, Art-Art, Publishing-Children's Books, Photography-Photography, Film & Video-Webseries, Publishing-Publishing, Film & Video-Narrative Film, Music-Hip-Hop, Crafts-Crafts, Technology-Web, Technology-Software, Design-Design, Food-Restaurants, Art-Painting, Technology-Hardware, Games-Games, Art-Mixed Media, Film & Video-Animation, Food-Drinks, Fashion-Accessories, Food-Food Trucks, Technology-Gadgets, Music-Electronic Music, Games-Mobile Games, Journalism-Journalism, Art-Performance Art, Film & Video-Comedy, Design-Graphic Design, Film & Video-Drama, Food-Small Batch, Music-World Music, Art-Sculpture, Games-Playing Cards, Journalism-Web, Publishing-Poetry, Food-Farms, Art-Digital Art, Crafts-DIY, Photography-People, Photography-Photobooks, Crafts-Woodworking, Film & Video-Television, Publishing-Periodicals, Film & Video-Horror, Games-Live Games, Fashion-Jewelry, Art-Conceptual Art, Fashion-Ready-to-wear, Photography-Places, Music-Faith, Publishing-Academic, Publishing-Young Adult, Film & Video-Action, Technology-Wearables, Food-Events, Design-Architecture, Publishing-Radio & Podcasts, Journalism-Print, Fashion-Footwear, Photography-Nature, Film & Video-Thrillers, Photography-Fine Art, Music-Metal, Film & Video-Music Videos, Film & Video-Science Fiction, Film & Video-Experimental, Food-Cookbooks, Journalism-Video, Food-Farmer's Markets, Technology-3D Printing, Crafts-Candles, Fashion-Childrenswear, Technology-Flight, Food-Vegan, Music-R&B, Design-Interactive Design, Technology-Robots, Technology-Sound, Journalism-Audio, Food-Spaces, Film & Video-Family, Food-Community Gardens, Games-Gaming Hardware, Fashion-Couture, Film & Video-Fantasy, Photography-Animals, Design-Civic Design, Publishing-Zines, Technology-Space Exploration, Food-Bacon, Film & Video-Movie Theaters, Art-Textiles, Technology-Fabrication Tools, Journalism-Photo, Publishing-Calendars, Art-Ceramics, Music-Kids, Crafts-Printing, Art-Video Art, Crafts-Crochet, Technology-Makerspaces, Music-Blues, Games-Puzzles, Crafts-Stationery, Film & Video-Romance, Publishing-Translations, Dance-Spaces, Dance-Workshops, Crafts-Glass, Comics-Events, Crafts-Embroidery, Fashion-Pet Fashion, Music-Latin, Crafts-Quilts, Crafts-Weaving, Crafts-Taxidermy


import plotly.graph_objects as go

dico2 = {k:((v[0]*100)/(v[0]+v[1]),(v[1]*100)/(v[0]+v[1])) for k,v in more_success_than_failed.items()}

fig = go.Figure(data=[
    go.Bar(name='Success Percent', x=list(dico2.keys()), y=[x[1] for x in list(dico2.values())]),
    go.Bar(name='Failed Percent', x=list(dico2.keys()), y=[x[0] for x in list(dico2.values())])
])
# Change the bar mode
fig.update_layout(barmode='stack',title=go.layout.Title(text="Percent of most successful in categories"))
fig.show()


main_goal_cat = df_final.groupby(['cat_full', 'state'], as_index=False)['usd_goal'].mean()
main_cats_failed = main_goal_cat[main_goal_cat["state"] == "failed"][main_goal_cat.cat_full.isin(list(more_success_than_failed.keys()))]
main_cats_success = main_goal_cat[main_goal_cat["state"] == "successful"][main_goal_cat.cat_full.isin(list(more_success_than_failed.keys()))]

#First plot
trace1 = go.Bar(
    x=main_cats_success.cat_full,
    y=main_cats_success.usd_goal,
    opacity=0.60,
    name="Successful Categories"
)

#Second plot
trace2 = go.Bar(
    x=main_cats_failed.cat_full,
    y=main_cats_failed.usd_goal,
    opacity=0.60,
    name="Failed Categories"
)

data = [trace1, trace2]
layout = go.Layout(barmode='overlay', title=go.layout.Title(text="Most success in categories"))

fig = go.Figure(
    data=data,
    layout=layout
)

iplot(fig)

<ipython-input-76-46785aed45c0>:2: UserWarning:

Boolean Series key will be reindexed to match DataFrame index.

<ipython-input-76-46785aed45c0>:3: UserWarning:

Boolean Series key will be reindexed to match DataFrame index.


import plotly.graph_objects as go

dico2 = {k:((v[0]*100)/(v[0]+v[1]),(v[1]*100)/(v[0]+v[1])) for k,v in more_failed_than_success.items()}

fig = go.Figure(data=[
    go.Bar(name='Success Percent', x=list(dico2.keys()), y=[x[1] for x in list(dico2.values())]),
    go.Bar(name='Failed Percent', x=list(dico2.keys()), y=[x[0] for x in list(dico2.values())])
])
# Change the bar mode
fig.update_layout(barmode='stack', title=go.layout.Title(text="Percent of most failed in categories"))
fig.show()


df_final[df_final['state']=='successful'].sort_values(['backers'], ascending=False).head()


df_final[df_final['state']=='successful'].sort_values(['usd_goal'], ascending=False).head()


df_final[df_final['state']=='successful'].sort_values(['real_usd_pledged'], ascending=False).head(10)


def plot_continuous_vars(data, column_name):
    plot_dims = (14, 8)
    fig, (ax1, ax2) = plt.subplots(ncols=2, sharey=False, figsize=plot_dims)
    sns.distplot(data[column_name], ax=ax1)
    sns.distplot(np.log1p(data[column_name]), ax=ax2)


plot_continuous_vars(df_final, 'usd_goal')

C:\Users\ymaricar\anaconda3\lib\site-packages\seaborn\distributions.py:2551: FutureWarning:

`distplot` is a deprecated function and will be removed in a future version. Please adapt your code to use either `displot` (a figure-level function with similar flexibility) or `histplot` (an axes-level function for histograms).

C:\Users\ymaricar\anaconda3\lib\site-packages\seaborn\distributions.py:2551: FutureWarning:

`distplot` is a deprecated function and will be removed in a future version. Please adapt your code to use either `displot` (a figure-level function with similar flexibility) or `histplot` (an axes-level function for histograms).


plot_continuous_vars(df_final, 'real_usd_pledged')

C:\Users\ymaricar\anaconda3\lib\site-packages\seaborn\distributions.py:2551: FutureWarning:

`distplot` is a deprecated function and will be removed in a future version. Please adapt your code to use either `displot` (a figure-level function with similar flexibility) or `histplot` (an axes-level function for histograms).

C:\Users\ymaricar\anaconda3\lib\site-packages\seaborn\distributions.py:2551: FutureWarning:

`distplot` is a deprecated function and will be removed in a future version. Please adapt your code to use either `displot` (a figure-level function with similar flexibility) or `histplot` (an axes-level function for histograms).


df_failed = df_final[df_final["state"] == "failed"]
df_sucess = df_final[df_final["state"] == "successful"]


# Add histogram data
failed = np.log(df_failed['usd_goal']+1)
success = np.log(df_sucess['usd_goal']+1)

trace1 = go.Histogram(
    x=failed,
    opacity=0.60, nbinsx=30, name='Goals Failed', histnorm='probability'
)
trace2 = go.Histogram(
    x=success,
    opacity=0.60, nbinsx=30, name='Goals Sucessful', histnorm='probability'
)

data = [trace1, trace2]
layout = go.Layout(barmode='overlay', title=go.layout.Title(text="Distributions of usd_goal"))

fig = go.Figure(
    data=data,
    layout=layout
)

iplot(fig)


import plotly.express as px
fig = px.box(df_final, x="main_category", y="usd_goal")
fig.show()


df_failed = df_final[df_final["state"] == "failed"]
df_success = df_final[df_final["state"] == "successful"]

plot_continuous_vars(df_failed, 'backers')
plot_continuous_vars(df_success, 'backers')

C:\Users\ymaricar\anaconda3\lib\site-packages\seaborn\distributions.py:2551: FutureWarning:

`distplot` is a deprecated function and will be removed in a future version. Please adapt your code to use either `displot` (a figure-level function with similar flexibility) or `histplot` (an axes-level function for histograms).

C:\Users\ymaricar\anaconda3\lib\site-packages\seaborn\distributions.py:2551: FutureWarning:

`distplot` is a deprecated function and will be removed in a future version. Please adapt your code to use either `displot` (a figure-level function with similar flexibility) or `histplot` (an axes-level function for histograms).

C:\Users\ymaricar\anaconda3\lib\site-packages\seaborn\distributions.py:2551: FutureWarning:

`distplot` is a deprecated function and will be removed in a future version. Please adapt your code to use either `displot` (a figure-level function with similar flexibility) or `histplot` (an axes-level function for histograms).

C:\Users\ymaricar\anaconda3\lib\site-packages\seaborn\distributions.py:2551: FutureWarning:

`distplot` is a deprecated function and will be removed in a future version. Please adapt your code to use either `displot` (a figure-level function with similar flexibility) or `histplot` (an axes-level function for histograms).

	ID	name	category	main_category	currency	deadline	goal	launched	pledged	state	backers	country	usd pledged
count	323716	323712	323716	323716	323716	323716	323716	323716	323716	323716	323716	323716	319879
unique	323716	321577	158	16	53	295323	7618	323220	55019	34	3583	54	94483
top	537793224	New EP/Music Development	Product Design	Film & Video	USD	2012-01-01 05:59:00	5000	1970-01-01 01:00:00	0	failed	0	US	0
freq	1	41	17503	57733	260752	47	25570	7	45873	168564	48955	258014	50553

	ID	name	category	main_category	currency	deadline	goal	launched	pledged	state	backers	country	usd pledged	tmp
6262	1037047712	Second Life Second Chance (my very first album )	Pop	USD	USD	2010-07-17 19:06:00	4000	2010-06-22 12:34:36	953	failed	19	US	953	Music
11153	1065173583	Help promote Strangefruit!	Fashion	USD	USD	2009-09-21 05:43:00	1500	2009-08-28 18:16:11	0	failed	0	US	0	Fashion
13225	1077797875	THE TORCH MUST KEEP BURNING! FUND THE NEW RECO...	Indie Rock	USD	USD	2011-02-11 19:19:44	6000	2010-12-13 19:19:44	1181	failed	9	US	1181	Music
26156	1154862705	Let's finish Katie Moore's new album together!	Country & Folk	USD	USD	2010-12-02 05:40:36	3000	2010-10-30 05:40:36	4581	successful	87	US	4581	Music
33867	1201238408	The Living Wetlands	Film & Video	USD	USD	2011-05-25 12:19:50	500	2011-02-23 12:19:50	45	failed	2	US	45	Film & Video
34817	1206936256	SAVE Blue Like Jazz! (the movie)	Narrative Film	USD	USD	2010-10-26 05:59:00	125000	2010-09-24 23:18:05	345992.47	successful	4495	US	345992.47	Film & Video
40953	1243737397	'A Taste of Happiness' a new CD of songs by ...	Music	USD	USD	2011-04-06 04:26:49	4000	2011-02-24 04:26:49	4451	successful	78	US	4451	Music
45947	1273172245	SHAKTI!	Narrative Film	USD	USD	2010-12-16 17:47:59	5000	2010-11-16 17:47:59	5117	successful	58	US	5117	Film & Video
60526	1359752672	A New Sudan Through War or Peace	Photography	USD	USD	2010-12-20 06:00:00	5000	2010-11-04 17:44:42	2001	failed	25	US	2001	Photography
71086	1422544453	An Artist in the ARCTIC RESIDENCY	Photography	USD	USD	2010-12-06 09:29:27	1300	2010-11-06 08:29:27	1340	successful	16	US	1340	Photography
75688	14498203	11 24: A Short Film About Collecting Cans and ...	Shorts	USD	USD	2011-04-25 21:17:35	1500	2011-01-24 21:17:35	1900	successful	40	US	1900	Film & Video
83402	1495194447	Murder Mystery Theatre Video Project	Theater	USD	USD	2011-03-20 04:11:03	600	2011-02-18 04:11:03	755	successful	18	US	755	Theater
94718	1562731910	The Genesis of images by Scott	Photography	USD	USD	2011-03-08 12:15:02	550	2010-12-08 12:15:02	25	failed	1	US	25	Photography
110033	165319510	15 A Feature Length Film (Canceled)	Narrative Film	USD	USD	2011-05-12 05:00:00	3600	2011-04-11 06:44:40	144	canceled	10	US	144	Film & Video
116504	1691556823	Suzanne Carrico's Debut Recording - What Chris...	Music	USD	USD	2010-08-31 23:07:00	5000	2010-07-26 23:52:25	5551	successful	65	US	5551	Music
140462	1834923380	Youth Choir fromSouth Africa needs a new home!	World Music	USD	USD	2010-11-23 20:27:20	35000	2010-10-24 20:27:20	0	failed	0	US	0	Music
141128	183917362	BROTHER LIAR JOHN - A Feature Film	Shorts	USD	USD	2011-03-18 22:00:00	4500	2011-02-01 13:56:26	131	failed	5	US	131	Film & Video
145290	1863308697	L'Amore della Musica Quintet's Concert Series ...	Classical Music	USD	USD	2011-03-21 18:58:31	5000	2011-02-19 19:58:31	5551	successful	66	US	5551	Music
146916	1872898319	Perishable Realities : Artist Exhibiton Funding	Art	USD	USD	2010-12-13 23:05:13	3500	2010-10-14 23:05:13	10	failed	1	US	10	Art
152208	1904422702	13th Dream	Film & Video	USD	USD	2011-01-19 23:15:24	5000	2010-10-21 23:15:24	25	failed	1	US	25	Film & Video
152732	1907771986	Fund A Mike Kuchar Film: Filmmaker Founded Un...	Film & Video	USD	USD	2010-08-13 02:16:00	600	2010-07-15 02:41:12	6	failed	2	US	6	Film & Video
164754	1979723427	Music Program for the Under Privileged	Music	USD	USD	2010-11-19 05:17:29	3000	2010-10-20 05:17:29	0	failed	0	US	0	Music
164790	1979950922	Deliver Flow Tribe's Next Funk Baby!	Music	USD	USD	2011-03-13 16:12:19	2000	2011-02-11 17:12:19	5135	successful	38	US	5135	Music
165475	1984073278	Essentials of Flor	Dance	USD	USD	2011-02-01 18:00:00	2500	2010-12-30 21:40:45	2980	successful	23	US	2980	Dance
166067	1987910949	White Buffalo Stands: Sacred Songs to Benefit ...	Music	USD	USD	2010-10-19 22:08:41	13500	2010-09-16 22:08:41	885	failed	9	US	885	Music
184709	2099851565	Expanding My Handmade Jewelry Collection!	Fashion	USD	USD	2011-04-13 08:11:00	5000	2011-03-06 20:42:34	5150	successful	72	US	5150	Fashion
189538	2128520745	IT’S A HOT CAPPUCCINO NIGHT	Fiction	USD	USD	2010-12-05 00:46:07	2000	2010-11-04 23:46:07	20	failed	1	US	20	Publishing
206036	294371724	A Solar Powered Music Project: Artist Residenc...	World Music	USD	USD	2010-12-16 11:04:40	4000	2010-11-06 10:04:40	635	failed	17	US	635	Music
209992	317893557	Native Americans Documentary	Documentary	USD	USD	2010-03-15 19:52:00	5000	2009-12-15 22:39:59	135	failed	3	US	135	Film & Video
247705	542758877	Recording of Wunmi's dream Album: Ghana or bust!	World Music	USD	USD	2010-02-08 05:59:00	15500	2009-11-23 05:22:29	17405	successful	81	US	17405	Music
251867	56795857	Gospel plays at the DC Black Theatre Festival!	Theater	USD	USD	2011-06-06 01:19:43	1000	2011-03-07 01:19:43	25	failed	1	US	25	Theater
253102	575325959	We promise once you have bit of Poundtastic	Food	USD	USD	2011-05-28 01:44:52	10000	2011-02-26 01:44:52	0	failed	0	US	0	Food
261877	628401820	Starving Artist Only Hungry for His Art	Hip-Hop	USD	USD	2011-01-07 18:36:43	6000	2010-11-23 18:36:43	0	failed	0	US	0	Music
268592	668533160	Visions of Johanne - A photo essay	Photography	USD	USD	2010-06-02 05:23:00	3000	2010-04-19 16:58:54	3070	successful	30	US	3070	Photography
273447	697713591	Movie Inspired by Actual Events	Documentary	USD	USD	2010-09-10 22:31:31	25000	2010-08-11 22:31:31	0	failed	0	US	0	Film & Video
279680	735066238	In Search of the Miraculous	Photography	USD	USD	2011-02-15 08:59:00	3900	2011-01-11 02:38:53	4540.99	successful	111	US	4540.99	Photography
287438	781972011	LONGEVITY -A PHOTO EXPLORATION INTO LOVE (FRANCE)	Photography	USD	USD	2009-11-16 05:59:00	4000	2009-10-04 19:12:44	95	failed	4	US	95	Photography
291705	807628947	Edgar White Recording Project	Indie Rock	USD	USD	2011-04-08 20:50:59	2500	2011-02-21 20:50:59	2906	successful	35	US	2906	Music
292593	813070034	The Prolific Needs Your Help To Create Their D...	Rock	USD	USD	2010-10-17 07:06:24	1200	2010-09-02 07:06:24	300	failed	5	US	300	Music
296204	834654830	Send EVOLVE LOVE Team to film the Climate Summ...	Documentary	USD	USD	2010-11-30 05:59:00	25000	2010-11-09 05:53:00	27871.88	successful	208	US	27871.88	Film & Video

	ID	name	category	main_category	currency	deadline	goal	launched	pledged	state	backers	country	usd pledged
count	323712	323712	323712	323712	323712	323712	323712	323712	323712	323712	323712	323712	319915
unique	323712	321600	158	15	13	295330	7578	323224	55020	6	3583	22	94486
top	537793224	New EP/Music Development	Product Design	Film & Video	USD	2012-01-01 05:59:00	5000	1970-01-01 01:00:00	0	failed	0	US	0
freq	1	41	17502	57743	260789	47	25577	7	45878	168583	48960	258051	50558

	ID	name	category	main_category	currency	deadline	goal	launched	pledged	state	backers	country	usd pledged	Unnamed: 13
32886	1195071984	The Polyamorous Socks - It's always a good match	)	Product Design	Design	SGD	2016-12-01 01:00:00	5000	2016-11-01 16:15:07	3300	failed	72	SG	2920.061449
33513	1199073018	Bear Witness- Too Cool For School Bus Tour (~)	} (Canceled)	Hip-Hop	Music	USD	2015-09-24 11:47:36	50000	2015-08-25 11:47:36	0	canceled	0	US	0.000000
36188	1215141595	The 1st Fun Children Books About How To Love O...	)	Children's Books	Publishing	EUR	2016-11-09 17:34:17	4000	2016-10-10 17:34:17	4287	successful	158	FR	2275.247857
36671	1218074363	I am Rupert	NaN	Webseries	Film & Video	GBP	2014-05-16 22:25:57	2000	2014-03-27 21:25:57	5	failed	1	GB	8.267797
41069	124438738	BlanketPals TM	NaN	Interactive Design	Design	USD	2015-03-25 20:51:48	9750	2015-02-23 21:51:48	10890.45	successful	107	US	10890.450000

	ID	name	category	main_category	currency	deadline	goal	launched	pledged	state	backers	country	usd pledged
count	323746	323746	323746	323746	323746	323746	323746	323746	323746	323746	323746	319949	319949
unique	323746	321634	158	15	13	295360	7578	323258	55023	6	3583	21	94516
top	537793224	New EP/Music Development	Product Design	Film & Video	USD	2012-01-01 05:59:00	5000	1970-01-01 01:00:00	0	failed	0	US	0
freq	1	41	17505	57745	260814	47	25580	7	45882	168605	48964	258076	50558

Kickstarter dataset project¶

Description¶

Reading and cleaning up the dataframe¶

Let's put the two dataframes back together¶

Exploratory Data Analysis¶

Recalculate real_usd_pledged and usd_goal¶

The following is outdated, the library is not maintained anymore. I'll load the final dataset for the following steps.¶

Leaving the code for information.¶

More EDA on the final dataframe¶

Categories and main_categories¶

Successful projects with the most backers¶

Successful projects with the highest goals¶

Successful projects with the highest pledges¶

Distribution of goals and pledges¶

	ID	name	category	main_category	currency	deadline	goal	launched	pledged	state	backers	country	usd pledged
0	1000002330	The Songs of Adelaide & Abullah	Poetry	Publishing	GBP	2015-10-09 11:36:00	1000	2015-08-11 12:12:28	0	failed	0	GB	0
1	1000004038	Where is Hank?	Narrative Film	Film & Video	USD	2013-02-26 00:20:50	45000	2013-01-12 00:20:50	220	failed	3	US	220
2	1000007540	ToshiCapital Rekordz Needs Help to Complete Album	Music	Music	USD	2012-04-16 04:24:11	5000	2012-03-17 03:24:11	1	failed	1	US	1
3	1000011046	Community Film Project: The Art of Neighborhoo...	Film & Video	Film & Video	USD	2015-08-29 01:00:00	19500	2015-07-04 08:35:03	1283	canceled	14	US	1283
4	1000014025	Monarch Espresso Bar	Restaurants	Food	USD	2016-04-01 13:38:27	50000	2016-02-26 13:38:27	52375	successful	224	US	52375

	ID	name	category	main_category	currency	deadline	goal	launched	pledged	state	backers	country	usd pledged
142830	1848699072	NaN	Narrative Film	Film & Video	USD	2012-02-29 15:04:00	200000	2012-01-01 12:35:31	100	failed	1	US	100
262901	634871725	NaN	Video Games	Games	GBP	2013-01-06 23:00:00	2000	2012-12-19 23:57:48	196	failed	12	GB	317.7284362
265251	648853978	NaN	Product Design	Design	USD	2016-07-18 05:01:47	2500	2016-06-18 05:01:47	0	suspended	0	US	0
289847	796533179	NaN	Painting	Art	USD	2011-12-05 05:59:00	35000	2011-11-06 23:55:55	220	failed	5	US	220

	currency	usd pledged	pledged
0	GBP	0.000000	0.0
1	USD	220.000000	220.0
2	USD	1.000000	1.0
4	USD	52375.000000	52375.0
5	USD	1205.000000	1205.0
...	...	...	...
323739	GBP	83.408540	50.0
323740	GBP	80.645161	52.0
323742	USD	850.000000	850.0
323743	USD	20.000000	20.0
323744	USD	545.000000	545.0

	ID	name	category	main_category	currency	deadline	launched	state	backers	country	real_usd_pledged	usd_goal
count	2.818530e+05	281853	281853	281853	281853	281853	281853	281853	281853.000000	281643	2.818530e+05	2.818530e+05
unique	NaN	280147	158	15	13	257784	281499	2	NaN	21	NaN	NaN
top	NaN	New EP/Music Development	Product Design	Film & Video	USD	2012-01-01 05:59:00	2015-08-31 19:43:05	failed	NaN	US	NaN	NaN
freq	NaN	15	14540	51130	229975	46	2	168605	NaN	229824	NaN	NaN
mean	1.074956e+09	NaN	NaN	NaN	NaN	NaN	NaN	NaN	111.852530	NaN	9.293935e+03	4.115817e+04
std	6.194665e+08	NaN	NaN	NaN	NaN	NaN	NaN	NaN	996.270201	NaN	9.314645e+04	1.082761e+06
min	5.971000e+03	NaN	NaN	NaN	NaN	NaN	NaN	NaN	0.000000	NaN	0.000000e+00	1.000000e-02
25%	5.373183e+08	NaN	NaN	NaN	NaN	NaN	NaN	NaN	2.000000	NaN	5.000000e+01	2.000000e+03
50%	1.075897e+09	NaN	NaN	NaN	NaN	NaN	NaN	NaN	15.000000	NaN	7.914802e+02	5.000000e+03
75%	1.611414e+09	NaN	NaN	NaN	NaN	NaN	NaN	NaN	62.000000	NaN	4.500000e+03	1.500000e+04
max	2.147476e+09	NaN	NaN	NaN	NaN	NaN	NaN	NaN	219382.000000	NaN	2.033899e+07	1.663627e+08

	ID	name	category	main_category	currency	deadline	launched	state	country	real_usd_pledged	usd_goal
1833	1012744036	An Oratorio for our Time - Last Stop Cafe	Music	Music	USD	2016-05-26 19:46:26	2016-04-26 19:46:26	successful	NaN	5170.00	5000.0
3670	1024989802	Jackson Ruby: The Cassette Album	Music	Music	USD	2016-05-11 19:29:17	2016-04-11 19:29:17	successful	NaN	5296.00	5000.0
4004	1027275369	Help Parker Brown make his first solo album	Music	Music	USD	2016-05-21 16:14:28	2016-04-21 16:14:28	successful	NaN	5077.00	3800.0
4180	1028691308	Help BETHANY record a NEW single in Nash!	Music	Music	USD	2016-05-08 22:37:00	2016-04-04 23:32:00	successful	NaN	3502.13	3500.0
6157	1041708793	Serena Gabriel's first CD!!!!!!: Diving Deep	Music	Music	USD	2016-05-01 04:22:00	2016-03-25 17:20:21	successful	NaN	3787.00	3500.0

	ID	name	category	main_category	currency	deadline	launched	state	backers	country	real_usd_pledged	usd_goal
1529	1010584633	"A Fresh Start"	Shorts	Film & Video	USD	2011-09-25 06:00:00	2011-08-28 21:27:52	successful	24	US	3000.0	3000.0
240126	713417995	"A Fresh Start"	Documentary	Film & Video	USD	2013-03-27 02:51:47	2013-01-26 03:51:47	failed	26	US	1417.0	5000.0
96268	1656736114	"ONE"	Apps	Technology	USD	2016-02-25 17:37:04	2016-01-26 17:37:04	failed	0	US	0.0	10000.0
86497	159049492	"ONE"	Classical Music	Music	USD	2016-09-26 03:19:12	2016-08-12 03:19:12	successful	113	US	10261.0	10000.0
281045	996180421	"On The Road"	Webseries	Film & Video	USD	2015-01-22 17:31:06	2014-12-23 17:31:06	failed	0	US	0.0	80000.0

	cat_full	category
count	281637	281637
unique	165	158
top	Design-Product Design	Product Design
freq	14538	14538

	ID	name	category	main_category	currency	deadline	launched	state	backers	country	real_usd_pledged	usd_goal	cat_full
139678	1955357092	Exploding Kittens	Tabletop Games	Games	USD	2015-02-20 03:00:00	2015-01-20 19:00:19	successful	219382	US	8782571.99	10000.0	Games-Tabletop Games
56611	1386523707	Fidget Cube: A Vinyl Desk Toy	Product Design	Design	USD	2016-10-20 03:00:00	2016-08-30 22:02:09	successful	154926	US	6465690.30	15000.0	Design-Product Design
217615	557230947	Bring Reading Rainbow Back for Every Child;Eve...	Web	Technology	USD	2014-07-02 21:00:00	2014-05-28 15:05:45	successful	105857	US	5408916.95	1000000.0	Technology-Web
110616	1755266685	The Veronica Mars Movie Project	Narrative Film	Film & Video	USD	2013-04-13 05:00:00	2013-03-13 15:42:22	successful	91585	US	5702153.38	2000000.0	Film & Video-Narrative Film
135994	1929840910	Double Fine Adventure	Video Games	Games	USD	2012-03-14 01:00:00	2012-02-09 02:52:52	successful	87142	US	3336371.92	400000.0	Games-Video Games

	ID	name	category	main_category	currency	deadline	launched	state	backers	country	real_usd_pledged	usd_goal	cat_full
264321	880009511	Elite: Dangerous	Video Games	Games	GBP	2013-01-05 01:00:57	2012-11-06 01:00:57	successful	25681	GB	2.528259e+06	2.002339e+06	Games-Video Games
66632	1454565733	Bring Back MYSTERY SCIENCE THEATER 3000	Television	Film & Video	USD	2015-12-12 07:00:00	2015-11-10 16:49:32	successful	48270	US	5.764229e+06	2.000000e+06	Film & Video-Television
274133	947809001	Shenmue 3	Video Games	Games	USD	2015-07-18 03:51:04	2015-06-16 03:51:04	successful	69320	US	6.333296e+06	2.000000e+06	Games-Video Games
127565	1871494789	WISH I WAS HERE	Narrative Film	Film & Video	USD	2013-05-24 21:00:00	2013-04-24 11:57:04	successful	46520	US	3.105473e+06	2.000000e+06	Film & Video-Narrative Film
100051	1682353635	Camelot Unchained	Video Games	Games	USD	2013-05-02 17:56:11	2013-04-02 17:56:11	successful	14873	US	2.232933e+06	2.000000e+06	Games-Video Games

	ID	name	category	main_category	currency	deadline	launched	state	backers	country	real_usd_pledged	usd_goal	cat_full
117102	1799979574	Pebble Time - Awesome Smartwatch;No Compromises	Product Design	Design	USD	2015-03-28 03:00:00	2015-02-24 15:44:42	successful	78471	US	20338986.27	500000.0	Design-Product Design
186319	342886736	COOLEST COOLER: 21st Century Cooler that's Act...	Product Design	Design	USD	2014-08-30 03:00:00	2014-07-08 10:14:37	successful	62642	US	13285226.36	50000.0	Design-Product Design
161210	2103598555	Pebble 2;Time 2 + All-New Pebble Core	Product Design	Design	USD	2016-06-30 07:00:00	2016-05-24 15:49:52	successful	66673	US	12779843.49	1000000.0	Design-Product Design
210261	506924864	Pebble: E-Paper Watch for iPhone and Android	Product Design	Design	USD	2012-05-19 05:00:00	2012-04-11 06:59:04	successful	68929	US	10266845.74	100000.0	Design-Product Design
218800	565687737	The World's Best TRAVEL JACKET with 15 Feature...	Product Design	Design	USD	2015-09-03 19:00:00	2015-07-07 13:52:34	successful	44949	US	9192055.66	20000.0	Design-Product Design
139678	1955357092	Exploding Kittens	Tabletop Games	Games	USD	2015-02-20 03:00:00	2015-01-20 19:00:19	successful	219382	US	8782571.99	10000.0	Games-Tabletop Games
4944	1033978702	OUYA: A New Kind of Video Game Console	Gaming Hardware	Games	USD	2012-08-09 07:00:00	2012-07-10 14:44:41	successful	63416	US	8596474.58	950000.0	Games-Gaming Hardware
201948	450099426	The Everyday Backpack;Tote;and Sling	Product Design	Design	USD	2016-09-10 02:00:00	2016-07-13 00:47:35	successful	26359	US	6565782.50	500000.0	Design-Product Design
56611	1386523707	Fidget Cube: A Vinyl Desk Toy	Product Design	Design	USD	2016-10-20 03:00:00	2016-08-30 22:02:09	successful	154926	US	6465690.30	15000.0	Design-Product Design
274133	947809001	Shenmue 3	Video Games	Games	USD	2015-07-18 03:51:04	2015-06-16 03:51:04	successful	69320	US	6333295.77	2000000.0	Games-Video Games